MFBTFF-Net: A Novel Multi-Frequency Brightness Temperature Feature Fusion Network for Global Lunar Surface Oxides Abundance Estimation With Chang'e-2 Lunar Microwave Sounder Data
Research on lunar oxides abundance has been spotlighted for its great significance in reconstructing the evolutionary history of the moon. In recent years, artificial intelligence technologies have been introduced to map oxides abundance on the lunar surface for their reliability and robustness. How...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10824911/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832576756990607360 |
|---|---|
| author | Yu Li Zifeng Yuan Sarah Mazhar Zhiguo Meng Yuanzhi Zhang Jinsong Ping Ferdinando Nunziata |
| author_facet | Yu Li Zifeng Yuan Sarah Mazhar Zhiguo Meng Yuanzhi Zhang Jinsong Ping Ferdinando Nunziata |
| author_sort | Yu Li |
| collection | DOAJ |
| description | Research on lunar oxides abundance has been spotlighted for its great significance in reconstructing the evolutionary history of the moon. In recent years, artificial intelligence technologies have been introduced to map oxides abundance on the lunar surface for their reliability and robustness. However, there are still some shortcomings in existing studies. First, the majority of these studies rely on spectral data and used in situ (drilled) ground truth samples collected by satellite missions. The detection depth of spectral sensors and the drilled depths of the returned samples are not consistent, lowering the reliability of the results. Moreover, existing machine/deep learning models may not be suitable for processing the data acquired in lunar exploration. In this article, we propose a novel deep learning model named multifrequency brightness temperature feature fusion network (MFBTFF-Net) for processing Chang'e-2 lunar microwave sounder (CELMS) data and it exploits the thermal radiation features related to various drilling depths to acquire the global lunar oxide abundance maps. The experimental results demonstrated that the proposed MFBTFF-Net model can significantly improve the estimation precision of most lunar oxides. The proposed method achieved root-mean-square error indices of 1.4449, 1.4826, and 0.9824 (wt.%) on estimating Al<sub>2</sub>O<sub>3</sub>, FeO, and TiO<sub>2</sub>, which outperformed the state-of-the-art models by at least 0.0674, 0.6217, and 0.0578, respectively. Furthermore, based on the proposed model, we generated a new set of lunar oxide abundance maps. Compared with the abundance maps derived from spectral data, some discoveries can be obtained due to the unique penetration depth-related information provided by Chang'e-2 CELMS data. This study demonstrates the large potential of Chang'e-2 CELMS as a powerful new tool to understand the vertical structures of the moon under the regolith. |
| format | Article |
| id | doaj-art-5b41f040fe964aa3b26f4c28d6f73330 |
| institution | Kabale University |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-5b41f040fe964aa3b26f4c28d6f733302025-01-31T00:00:14ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01183921394210.1109/JSTARS.2025.352579710824911MFBTFF-Net: A Novel Multi-Frequency Brightness Temperature Feature Fusion Network for Global Lunar Surface Oxides Abundance Estimation With Chang'e-2 Lunar Microwave Sounder DataYu Li0https://orcid.org/0000-0002-5693-5353Zifeng Yuan1https://orcid.org/0000-0001-6193-3507Sarah Mazhar2Zhiguo Meng3https://orcid.org/0000-0002-4598-087XYuanzhi Zhang4https://orcid.org/0000-0002-9244-8464Jinsong Ping5Ferdinando Nunziata6https://orcid.org/0000-0003-4567-0377School of Information Science and Technology, Beijing University of Technology, Beijing, ChinaSchool of Information Science and Technology, Beijing University of Technology, Beijing, ChinaSchool of Information Science and Technology, Beijing University of Technology, Beijing, ChinaCollege of Geoexploration Science and Technology, Jilin University, Changchun, ChinaKey Laboratory of Lunar and Deep Space Exploration, National Astronomical Observatories, Chinese Academy of Sciences, Beijing, ChinaKey Laboratory of Lunar and Deep Space Exploration, National Astronomical Observatories, Chinese Academy of Sciences, Beijing, ChinaDipartimento di Ingegneria dell'Informazione, Elettronica e Telecomunicazioni, Sapienza Università di Roma, Roma, ItalyResearch on lunar oxides abundance has been spotlighted for its great significance in reconstructing the evolutionary history of the moon. In recent years, artificial intelligence technologies have been introduced to map oxides abundance on the lunar surface for their reliability and robustness. However, there are still some shortcomings in existing studies. First, the majority of these studies rely on spectral data and used in situ (drilled) ground truth samples collected by satellite missions. The detection depth of spectral sensors and the drilled depths of the returned samples are not consistent, lowering the reliability of the results. Moreover, existing machine/deep learning models may not be suitable for processing the data acquired in lunar exploration. In this article, we propose a novel deep learning model named multifrequency brightness temperature feature fusion network (MFBTFF-Net) for processing Chang'e-2 lunar microwave sounder (CELMS) data and it exploits the thermal radiation features related to various drilling depths to acquire the global lunar oxide abundance maps. The experimental results demonstrated that the proposed MFBTFF-Net model can significantly improve the estimation precision of most lunar oxides. The proposed method achieved root-mean-square error indices of 1.4449, 1.4826, and 0.9824 (wt.%) on estimating Al<sub>2</sub>O<sub>3</sub>, FeO, and TiO<sub>2</sub>, which outperformed the state-of-the-art models by at least 0.0674, 0.6217, and 0.0578, respectively. Furthermore, based on the proposed model, we generated a new set of lunar oxide abundance maps. Compared with the abundance maps derived from spectral data, some discoveries can be obtained due to the unique penetration depth-related information provided by Chang'e-2 CELMS data. This study demonstrates the large potential of Chang'e-2 CELMS as a powerful new tool to understand the vertical structures of the moon under the regolith.https://ieeexplore.ieee.org/document/10824911/Brightness temperatureChang'e-2 lunar microwave sounder (CELMS)deep neural network (NN)lunar oxides abundance |
| spellingShingle | Yu Li Zifeng Yuan Sarah Mazhar Zhiguo Meng Yuanzhi Zhang Jinsong Ping Ferdinando Nunziata MFBTFF-Net: A Novel Multi-Frequency Brightness Temperature Feature Fusion Network for Global Lunar Surface Oxides Abundance Estimation With Chang'e-2 Lunar Microwave Sounder Data IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Brightness temperature Chang'e-2 lunar microwave sounder (CELMS) deep neural network (NN) lunar oxides abundance |
| title | MFBTFF-Net: A Novel Multi-Frequency Brightness Temperature Feature Fusion Network for Global Lunar Surface Oxides Abundance Estimation With Chang'e-2 Lunar Microwave Sounder Data |
| title_full | MFBTFF-Net: A Novel Multi-Frequency Brightness Temperature Feature Fusion Network for Global Lunar Surface Oxides Abundance Estimation With Chang'e-2 Lunar Microwave Sounder Data |
| title_fullStr | MFBTFF-Net: A Novel Multi-Frequency Brightness Temperature Feature Fusion Network for Global Lunar Surface Oxides Abundance Estimation With Chang'e-2 Lunar Microwave Sounder Data |
| title_full_unstemmed | MFBTFF-Net: A Novel Multi-Frequency Brightness Temperature Feature Fusion Network for Global Lunar Surface Oxides Abundance Estimation With Chang'e-2 Lunar Microwave Sounder Data |
| title_short | MFBTFF-Net: A Novel Multi-Frequency Brightness Temperature Feature Fusion Network for Global Lunar Surface Oxides Abundance Estimation With Chang'e-2 Lunar Microwave Sounder Data |
| title_sort | mfbtff net a novel multi frequency brightness temperature feature fusion network for global lunar surface oxides abundance estimation with chang x0027 e 2 lunar microwave sounder data |
| topic | Brightness temperature Chang'e-2 lunar microwave sounder (CELMS) deep neural network (NN) lunar oxides abundance |
| url | https://ieeexplore.ieee.org/document/10824911/ |
| work_keys_str_mv | AT yuli mfbtffnetanovelmultifrequencybrightnesstemperaturefeaturefusionnetworkforgloballunarsurfaceoxidesabundanceestimationwithchangx0027e2lunarmicrowavesounderdata AT zifengyuan mfbtffnetanovelmultifrequencybrightnesstemperaturefeaturefusionnetworkforgloballunarsurfaceoxidesabundanceestimationwithchangx0027e2lunarmicrowavesounderdata AT sarahmazhar mfbtffnetanovelmultifrequencybrightnesstemperaturefeaturefusionnetworkforgloballunarsurfaceoxidesabundanceestimationwithchangx0027e2lunarmicrowavesounderdata AT zhiguomeng mfbtffnetanovelmultifrequencybrightnesstemperaturefeaturefusionnetworkforgloballunarsurfaceoxidesabundanceestimationwithchangx0027e2lunarmicrowavesounderdata AT yuanzhizhang mfbtffnetanovelmultifrequencybrightnesstemperaturefeaturefusionnetworkforgloballunarsurfaceoxidesabundanceestimationwithchangx0027e2lunarmicrowavesounderdata AT jinsongping mfbtffnetanovelmultifrequencybrightnesstemperaturefeaturefusionnetworkforgloballunarsurfaceoxidesabundanceestimationwithchangx0027e2lunarmicrowavesounderdata AT ferdinandonunziata mfbtffnetanovelmultifrequencybrightnesstemperaturefeaturefusionnetworkforgloballunarsurfaceoxidesabundanceestimationwithchangx0027e2lunarmicrowavesounderdata |